import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import statsmodels.api as sm
import plotly.express as px
import plotly.graph_objs as go

from scipy.stats import chi2_contingency
from scipy import stats
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.utils import resample
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.impute import SimpleImputer
from imblearn.over_sampling import SMOTE
from sklearn.naive_bayes import GaussianNB 
from sklearn .ensemble import VotingClassifier , BaggingClassifier , StackingClassifier 
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn import preprocessing
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LassoLars
from sklearn.linear_model import RidgeCV
from sklearn.datasets import make_classification
from sklearn.metrics import accuracy_score, classification_report, roc_auc_score, roc_curve, confusion_matrix
from sklearn.preprocessing import LabelEncoder

le = preprocessing.LabelEncoder()

import warnings 
warnings.filterwarnings('ignore')

print('Modules are imported.')

Modules are imported.

stroke_data = pd.read_csv(r'C:\Users\user\Downloads\healthcare-dataset-stroke-data.csv')

# Display the first few rows of the stroke_data DataFrame
stroke_data.head()

# Get the shape of the DataFrame
stroke_data.shape

(5110, 12)

# Display concise summary information about the stroke_data DataFrame
stroke_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5110 entries, 0 to 5109
Data columns (total 12 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   id                 5110 non-null   int64  
 1   gender             5110 non-null   object 
 2   age                5110 non-null   float64
 3   hypertension       5110 non-null   int64  
 4   heart_disease      5110 non-null   int64  
 5   ever_married       5110 non-null   object 
 6   work_type          5110 non-null   object 
 7   Residence_type     5110 non-null   object 
 8   avg_glucose_level  5110 non-null   float64
 9   bmi                4909 non-null   float64
 10  smoking_status     5110 non-null   object 
 11  stroke             5110 non-null   int64  
dtypes: float64(3), int64(4), object(5)
memory usage: 479.2+ KB

# Generate descriptive statistics of the stroke_data DataFrame
stroke_data.describe()

# Continuous variables
stroke_data.hist(bins=30, figsize=(15,10))
plt.tight_layout()
plt.show()

# Visualization and distribution of the different variables in the stroke_data dataset as histograms

# Creating an independent copy of the DataFrame stroke_data and storing it in a new variable stroke_data2
stroke_data2 = stroke_data.copy()

# STROKE STATUS

# Replace values in the 'stroke' column
stroke_data2['stroke'] = stroke_data2['stroke'].replace({1: 'Yes', 0: 'No'})

# Count the occurrences of different values in the 'stroke' column
stroke_counts = stroke_data2['stroke'].value_counts().reset_index()
stroke_counts.columns = ['Stroke', 'Count']

# Define custom colors
custom_colors = ['#252E6C', '#FF4500']

# Create the pie chart
fig, ax = plt.subplots()
pie = ax.pie(stroke_counts['Count'], labels=stroke_counts['Stroke'], colors=custom_colors, autopct='%1.1f%%', startangle=90, wedgeprops={'edgecolor': 'black'})

# Add a title
plt.title('Distribution of Stroke Status')

# Add a legend with specified labels and modified position
plt.legend(pie[0], ['No Stroke', 'Stroke'], loc="center left", bbox_to_anchor=(1, 0.5))

# Display the chart
plt.tight_layout()
plt.show()

# GENDER DISTRIBUTION

# Count the occurrences of different values in the 'gender' column
gender_counts = stroke_data['gender'].value_counts()

# Define custom colors
custom_colors = ['#FF69B4', '#252E6C', '#90EE90']

# Create the bar chart
fig, ax = plt.subplots()
bars = ax.bar(gender_counts.index, gender_counts.values, color=custom_colors)

# Add labels for each bar
for bar in bars:
    height = bar.get_height()
    ax.annotate('{}'.format(height),
                xy=(bar.get_x() + bar.get_width() / 2, height),
                xytext=(0, 3),  # 3 points above the bar
                textcoords="offset points",
                ha='center', va='bottom')

# Add a title
plt.title('Gender Distribution')

# Display the chart
plt.show()

#STROKE CASES BY GENDER

# Count the occurrences of different values in the 'gender' and 'stroke' columns, then group them
gender_stroke_counts = stroke_data.groupby(['gender', 'stroke']).size().unstack()

# Calculate the percentage of stroke cases for each gender
gender_stroke_percentage = (gender_stroke_counts[1] / (gender_stroke_counts[0] + gender_stroke_counts[1])) * 100

# Create a pie chart with Plotly Express
fig = px.pie(names=gender_stroke_percentage.index, values=gender_stroke_percentage.values,
             title="Percentage of Stroke Cases by Gender",
             color_discrete_sequence=['#252E6C', '#FF69B4'])

# Update chart traces
fig.update_traces(textinfo="percent+label", pull=[0.1, 0], marker=dict(line=dict(color="white", width=2)))

# Display the chart
fig.show()

# STROKE DISTRIBUTION BY AGE

# Group the data by age and stroke status, then count the occurrences of each combination
age_stroke_counts = stroke_data2.groupby(["age", "stroke"]).size().reset_index(name="Count")

# Create a scatter plot with Plotly Express
fig_bubble_age_stroke = px.scatter(age_stroke_counts, x="age", y="Count", size="Count", color="stroke",
                                   title="Stroke Distribution by Age",
                                   labels={"age": "Age", "Count": "Count", "stroke": "Stroke"},
                                   color_discrete_sequence=['#252E6C', '#FF4500'])

# Update the layout of the plot
fig_bubble_age_stroke.update_layout(xaxis_title="Age", yaxis_title="Count")

# Display the plot
fig_bubble_age_stroke.show()

# Calculate the t-statistic and p-value for age
t_stat_age, p_value_age = stats.ttest_ind(stroke_data[stroke_data['stroke'] == 1]['age'],
                                           stroke_data[stroke_data['stroke'] == 0]['age'])

# Display the t-test results for age
print(f'T-test for age - T-statistic: {t_stat_age}, P-value: {p_value_age}')

T-test for age - T-statistic: 18.08083426887953, P-value: 7.0307775129939774e-71

# Create the box plot

# Set the figure size
plt.figure(figsize=(10, 6))

# Plot the box plot
sns.boxplot(x='stroke', y='age', data=stroke_data, palette=['blue', 'red'])

# Add labels for x and y axes, and a title
plt.xlabel('Stroke')
plt.ylabel('Age')
plt.title('Box Plot of Age by Stroke Status')

# Rename x-axis ticks
plt.xticks([0, 1], ['No Stroke', 'Stroke'])

# Show the box plot
plt.show()

# DISTRIBUTION OF HYPERTENSION

# Replace values in the 'hypertension' column
stroke_data2['hypertension'] = stroke_data2['hypertension'].replace({1: 'Yes', 0: 'No'})

# Count the occurrences of different values in the 'hypertension' column
hypertension_count = stroke_data2['hypertension'].value_counts()

# Define custom colors
custom_colors = ['#252E6C', '#90EE90']

# Create a pie chart with Plotly Express
fig = px.pie(
    values=hypertension_count,  # Values to be represented
    names=hypertension_count.index,  # Names of the categories
    hole=0.3,  # Size of the hole in the center of the chart (0 for no hole)
    title='Distribution of Patients with and without Hypertension',  # Chart title
    color_discrete_sequence=custom_colors,  # Custom color sequence
)

# Update chart traces to include text information about percentages and labels,
# and pull one of the sectors to highlight it
fig.update_traces(textinfo='percent+label', pull=[0, 0.1])

# Display the chart
fig.show()

# Calculate the stroke rate with and without hypertension
stroke_rate_with_hypertension = (stroke_data[stroke_data['hypertension'] == 1]['stroke'].mean()) * 100
stroke_rate_without_hypertension = (stroke_data[stroke_data['hypertension'] == 0]['stroke'].mean()) * 100

# Create a DataFrame containing the data
data = pd.DataFrame({'Hypertension': ['With Hypertension', 'Without Hypertension'],
                     'Stroke Rate': [stroke_rate_with_hypertension, stroke_rate_without_hypertension]})

# Create a bar chart with Plotly Express
fig = px.bar(data, x='Hypertension', y='Stroke Rate',
             text='Stroke Rate', title='Stroke Rate by Hypertension',
             labels={'Hypertension': 'Hypertension Status', 'Stroke Rate': 'Stroke Rate (%)'})

# Update the colors of the bars
fig.update_traces(marker_color=["#123F6A", "#89AED2"])

# Update the position and format of the label text
fig.update_traces(texttemplate='%{text:.2f}%', textposition='outside')

# Display the chart
fig.show()

# Create a contingency table for hypertension and stroke status
contingency_table = pd.crosstab(stroke_data['hypertension'], stroke_data['stroke'])

# Perform the chi-square test on the contingency table
chi2, p, dof, expected = chi2_contingency(contingency_table)

# Display the results of the chi-square test
print('Chi-square test for hypertension - Chi2:', chi2, ', P-value:', p)

Chi-square test for hypertension - Chi2: 81.6053682482931 , P-value: 1.661621901511823e-19

# DISTRIBUTION OF HEART DISEASE BY STROKE

# Replace values in the 'heart_disease' column
stroke_data2['heart_disease'] = stroke_data2['heart_disease'].replace({1: 'Yes', 0: 'No'})

# Separate data for patients who had a stroke and those who did not
heart_disease_yes = stroke_data2[stroke_data2["stroke"] == "Yes"]["heart_disease"]
heart_disease_no = stroke_data2[stroke_data2["stroke"] == "No"]["heart_disease"]

# Prepare data for the histogram
hist_data_heart_disease = [heart_disease_yes, heart_disease_no]
group_labels_heart_disease = ["Stroke: Yes", "Stroke: No"]
colors_heart_disease = ['#FF4500', '#252E6C']

# Create a Figure object (fig_heart_disease) with Plotly
fig_heart_disease = go.Figure()

# Add histograms for both groups (with and without stroke)
for i in range(2):
    fig_heart_disease.add_trace(go.Histogram(x=hist_data_heart_disease[i], nbinsx=10, opacity=0.7,
                                              name=group_labels_heart_disease[i], marker_color=colors_heart_disease[i]))

# Update the layout of the chart (title, axis titles)
fig_heart_disease.update_layout(title="Distribution of Heart Disease by Stroke",
                                 xaxis_title="Heart Disease", yaxis_title="Frequency")

# Display the chart
fig_heart_disease.show()

# Create a contingency table for heart diseases and stroke status
contingency_table = pd.crosstab(stroke_data['heart_disease'], stroke_data['stroke'])

# Perform the chi-square test on the contingency table
chi2, p, dof, expected = chi2_contingency(contingency_table)

# Display the results of the chi-square test
print('Chi-square test for heart diseases - Chi2:', chi2, ', P-value:', p)

Chi-square test for heart diseases - Chi2: 90.25956125843324 , P-value: 2.0887845685229236e-21

# STROKE RATE BY MARITAL STATUS

# Group the data by marital status and count the occurrences of each combination with or without stroke
attrition_by_ever_married = stroke_data2.groupby("ever_married")["stroke"].value_counts(normalize=True).unstack().reset_index()

# Define custom colors
custom_colors = ['#252E6C', '#010408']

# Create a pie chart with Plotly Express
fig_pie_ever_married = px.pie(attrition_by_ever_married, values="Yes", names="ever_married", hole=0.4,
                              title="Stroke Rate by Marital Status",
                              labels={"ever_married": "Ever Married"},
                              color_discrete_map={'Yes': custom_colors[0], 'No': custom_colors[1]})

# Update chart traces to include text information about percentages and labels,
# and pull one of the sectors to highlight it
fig_pie_ever_married.update_traces(textinfo="percent+label", pull=[0.1, 0.1], showlegend=False)

# Update the layout of the chart to include an annotation indicating the title of the chart
fig_pie_ever_married.update_layout(annotations=[dict(text="Stroke Rate", x=0.5, y=0.5, font_size=20, showarrow=False)])

# Display the chart
fig_pie_ever_married.show()

# Create a contingency table for marital status and stroke status
contingency_table = pd.crosstab(stroke_data['ever_married'], stroke_data['stroke'])

# Perform the chi-square test on the contingency table
chi2, p, dof, expected = chi2_contingency(contingency_table)

# Display the results of the chi-square test
print('Chi-square test for marital status - Chi2:', chi2, ', P-value:', p)

Chi-square test for marital status - Chi2: 58.923890259034195 , P-value: 1.6389021142314745e-14

# STROKE RATE BY WORK TYPE

# Group the data by work type and calculate the average stroke rate for each group
work_stroke_rates = stroke_data.groupby("work_type")["stroke"].mean().reset_index()

# Define the custom color for the bars in the chart
colors = ['#006400']

# Create a bar chart with Plotly Express
fig = px.bar(work_stroke_rates, x="work_type", y="stroke", 
             title="Stroke Rate by Work Type",
             labels={"work_type": "Work Type", "stroke": "Stroke Rate"},
             color_discrete_sequence=colors) 

# Update the layout of the chart with axis titles
fig.update_layout(xaxis_title="Work Type", yaxis_title="Stroke Rate")

# Display the chart
fig.show()

# Create a contingency table for work type and stroke status
contingency_table = pd.crosstab(stroke_data['work_type'], stroke_data['stroke'])

# Perform the chi-square test on the contingency table
chi2, p, dof, expected = chi2_contingency(contingency_table)

# Display the results of the chi-square test
print('Chi-square test for work type - Chi2:', chi2, ', P-value:', p)

Chi-square test for work type - Chi2: 49.163511976675295 , P-value: 5.397707801896119e-10

# STROKE STATUS BY RESIDENCE TYPE

# Group the data by residence type and stroke status, then count the occurrences
residence_stroke_counts = stroke_data2.groupby(['Residence_type', 'stroke']).size().unstack().reset_index()

# Rename the columns for clarity
residence_stroke_counts.columns = ['Residence_type', 'No', 'Yes']

# Define custom colors for the bars
custom_colors = ['#252E6C', '#FF4500']

# Create a stacked bar chart with Plotly Express
fig = px.bar(residence_stroke_counts, x='Residence_type', y=['No', 'Yes'],
             title='Distribution of Stroke Status by Residence Type',
             color_discrete_sequence=custom_colors,
             labels={'variable': 'Stroke', 'value': 'Count'})

# Update the x-axis labels to display the column names "Rural" and "Urban"
fig.update_xaxes(tickvals=[0, 1], ticktext=['Rural', 'Urban'])

# Update the layout of the chart to specify axis ranges
fig.update_layout(
    yaxis=dict(range=[0, residence_stroke_counts[['No', 'Yes']].values.max() * 1.1])  # Start at 0 on the y-axis
)

# Display the chart
fig.show()

# Create a contingency table for residence type and stroke status
contingency_table = pd.crosstab(stroke_data['Residence_type'], stroke_data['stroke'])

# Perform the chi-square test on the contingency table
chi2, p, dof, expected = chi2_contingency(contingency_table)

# Display the results of the chi-square test
print('Chi-square test for Residence type - Chi2:', chi2, ', P-value:', p)

Chi-square test for Residence type - Chi2: 1.0816367471627524 , P-value: 0.29833169286876987

# AVERAGE GLUCOSE LEVEL

# Display the minimum average glucose level
print(stroke_data['avg_glucose_level'].min())

# Display the maximum average glucose level
print(stroke_data['avg_glucose_level'].max())

# Define the boundaries for the average glucose level groups
glucose_bins = [55.12, 70, 99, 125, 271.74]

# Define the labels for the average glucose level groups
glucose_labels = ['Low', 'Normal', 'Pre-Diabetes', 'Diabetes']

# Create a new column in the DataFrame to group the average glucose levels
stroke_data2['avg_glucose_level_group'] = pd.cut(stroke_data2['avg_glucose_level'], bins=glucose_bins, labels=glucose_labels, right=False)

# Display the first few rows of the DataFrame to check the average glucose level groups
print(stroke_data2[['avg_glucose_level', 'avg_glucose_level_group']].head())

55.12
271.74
   avg_glucose_level avg_glucose_level_group
0             228.69                Diabetes
1             202.21                Diabetes
2             105.92            Pre-Diabetes
3             171.23                Diabetes
4             174.12                Diabetes

# STROKE BY AVERAGE GLUCOSE

# Define a custom color palette
custom_palette = ['#FF4500', '#252E6C']  # Changing the colors

# Create a figure of specific size
plt.figure(figsize=(10, 6))

# Create a countplot to show the distribution of stroke cases by average glucose level group
ax = sns.countplot(data=stroke_data2, x='avg_glucose_level_group', hue='stroke', palette=custom_palette)

# Add a title to the plot
plt.title("Stroke Incidence by Average Glucose Level Group")

# Add a label to the x-axis
plt.xlabel("Average Glucose Level Group")

# Add a label to the y-axis
plt.ylabel("Count")

# Add annotations for each bar in the plot
for p in ax.patches:
    height = p.get_height()
    ax.annotate(f"{int(height)}", (p.get_x() + p.get_width() / 2., height), ha='center', va='bottom')

# Add a legend with a title and labels
plt.legend(title="Stroke", labels=["Yes", "No"])

# Rotate the x-axis labels for better readability
plt.xticks(rotation=45)

# Add a grid for easier reading of values
plt.grid(True)

# Display the plot
plt.show()

# Perform a Student's t-test to compare the average glucose levels between individuals who had a stroke and those who did not

# Calculate the t-statistic and the p-value
t_stat_glucose, p_value_glucose = stats.ttest_ind(
    stroke_data[stroke_data['stroke'] == 1]['avg_glucose_level'],  # Average glucose levels for individuals who had a stroke
    stroke_data[stroke_data['stroke'] == 0]['avg_glucose_level']   # Average glucose levels for individuals who did not have a stroke
)

# Display the results of the t-test
print(f'Test t for average glucose level - t-statistic: {t_stat_glucose}, P-value: {p_value_glucose}')

Test t for average glucose level - t-statistic: 9.513352175431471, P-value: 2.7678105194741054e-21

# Create a figure with a specific size
plt.figure(figsize=(10, 6))

# Create a box plot for the average glucose level, based on the presence or absence of a stroke
sns.boxplot(
    x='stroke',  # Categorical variable indicating the presence or absence of a stroke
    y='avg_glucose_level',  # Continuous variable indicating the average glucose level
    data=stroke_data,  # DataFrame containing the data
    palette=['blue', 'red']  # Colors for the categories "No Stroke" and "Stroke"
)

# Add a label to the x-axis
plt.xlabel('Stroke')

# Add a label to the y-axis
plt.ylabel('Average Glucose Level')

# Add a title to the plot
plt.title('Box Plot of Average Glucose Level by Stroke Status')

# Modify the tick labels on the x-axis to indicate "No Stroke" and "Stroke"
plt.xticks([0, 1], ['No Stroke', 'Stroke'])

# Display the plot
plt.show()

# BMI GROUP

# Define the classification intervals for BMI
bmi_bins = [10, 18.5, 24.9, 29.9, 34.9, 39.9, 50, float('inf')]

# Define corresponding labels for each interval
bmi_labels = ['Underweight', 'Normal', 'Overweight', 'Obese Class I', 'Obese Class II', 'Obese Class III', 'Extreme Obesity']

# Create a new column 'bmi_group' in the DataFrame using the pd.cut function to categorize BMI values
stroke_data2['bmi_group'] = pd.cut(stroke_data2['bmi'], bins=bmi_bins, labels=bmi_labels, right=False)

# Display the minimum BMI value in the DataFrame
print(stroke_data2['bmi'].min())

# Display the maximum BMI value in the DataFrame
print(stroke_data2['bmi'].max())

# Display the first five rows of the DataFrame with the columns 'bmi' and 'bmi_group'
print(stroke_data2[['bmi', 'bmi_group']].head())

10.3
97.6
    bmi       bmi_group
0  36.6  Obese Class II
1   NaN             NaN
2  32.5   Obese Class I
3  34.4   Obese Class I
4  24.0          Normal

# STROKE BY BMI

# Group the data by 'bmi_group' and 'stroke', then count the occurrences in each group
bmi_stroke_counts = stroke_data2.groupby(['bmi_group', 'stroke']).size().reset_index(name='Count')

# Create a bar chart with Plotly Express
fig = px.bar(
    bmi_stroke_counts,  # Data to use for the chart
    x='bmi_group',      # Column to use for the x-axis
    y='Count',          # Column to use for the y-axis
    color='stroke',     # Column to use for bar colors
    title='Distribution of Strokes by BMI Group',  # Chart title
    labels={            # Labels to use for axes and legend
        'bmi_group': 'BMI Group',
        'Count': 'Count',
        'stroke': 'Stroke'
    },
    color_discrete_sequence=['#252E6C', '#FF4500']  # Color sequence for the bars
)

# Update the layout of the chart for axis titles and legend
fig.update_layout(
    xaxis_title='BMI Group',  # x-axis title
    yaxis_title='Count',      # y-axis title
    legend_title='Stroke'     # Legend title
)

# Display the chart
fig.show()

# Perform a t-test to compare BMI levels between groups with and without a stroke
t_stat_bmi, p_value_bmi = stats.ttest_ind(
    stroke_data[stroke_data['stroke'] == 1]['bmi'],  # BMI levels for individuals who had a stroke
    stroke_data[stroke_data['stroke'] == 0]['bmi']   # BMI levels for individuals who did not have a stroke
)

# Display the results of the t-test
print(f'Test t for bmi - t-statistic: {t_stat_bmi}, P-value: {p_value_bmi}')

Test t for bmi - t-statistic: nan, P-value: nan

# Create the box plot for BMI by stroke status

# Set the size of the figure
plt.figure(figsize=(10, 6))

# Create the box plot with the specified colors
sns.boxplot(x='stroke', y='bmi', data=stroke_data, palette=['blue', 'red'])

plt.xlabel('Stroke')  # Label the x-axis
plt.ylabel('BMI')  # Label the y-axis
plt.title('Box Plot of BMI by Stroke Status')  # Add a title to the plot
plt.xticks([0, 1], ['No Stroke', 'Stroke'])  # Set the labels for the x-values

# Display the plot
plt.show()

# SMOKIG STATUS DISTRIBUTION

# Count the occurrences of each smoking status and reset the index to obtain a DataFrame
smoking_status_counts = stroke_data['smoking_status'].value_counts().reset_index()

# Rename the columns of the DataFrame for clarity
smoking_status_counts.columns = ['smoking_status', 'count']

# Define custom colors for each smoking status
custom_colors = ['#FF6347', '#4682B4', '#32CD32', '#FFD700']

# Create a bar chart with Plotly Express
fig = px.bar(
    smoking_status_counts,  # Data to use for the chart
    x='smoking_status',     # Column to use for the x-axis
    y='count',              # Column to use for the y-axis
    title='Smoking Status Distribution',  # Chart title
    color='smoking_status',  # Column to use for bar colors
    color_discrete_sequence=custom_colors  # Custom color sequence for the bars
)

# Display the chart
fig.show()

# STROKE DISTRIBUTION BY SMOKING STATUS

# Group the data by 'smoking_status' and 'stroke', then count the occurrences and rearrange the columns
smoking_stroke_counts = stroke_data2.groupby(['smoking_status', 'stroke']).size().unstack().fillna(0).reset_index()

# Define custom colors for each smoking status
custom_colors = ['#FF6347', '#32CD32', '#4682B4', '#FFD700']

# Create a pie chart with Plotly Express
fig = px.pie(
    smoking_stroke_counts,  # Data to use for the chart
    names='smoking_status',  # Column to use for sector labels
    values='Yes',  # Column to use for sector values
    title='Stroke Distribution by Smoking Status',  # Chart title
    color_discrete_sequence=custom_colors  # Custom color sequence for the sectors
)

# Update the chart traces to add a hole in the center and display information as percent + label
fig.update_traces(hole=0.4, textinfo='percent+label')

# Display the chart
fig.show()

# Create a contingency table for smoking status and stroke status
contingency_table = pd.crosstab(stroke_data['smoking_status'], stroke_data['stroke'])

# Perform the chi-square test on the contingency table
chi2, p, dof, expected = chi2_contingency(contingency_table)

# Display the results of the chi-square test
print('Chi-square test for smoking status - Chi2:', chi2, ', P-value:', p)

Chi-square test for smoking status - Chi2: 29.147269191399264 , P-value: 2.0853997025008455e-06

# AGE GROUP

# Define the bins for age groups
age_bins = [0, 20, 40, 60, 80, float('inf')]

# Define the labels for each age group
age_labels = ['0-20', '21-40', '41-60', '61-80', '81+']

# Create a new column 'age_group' in the DataFrame 'stroke_data2' by categorizing ages according to the defined bins
stroke_data2['age_group'] = pd.cut(stroke_data2['age'], bins=age_bins, labels=age_labels, right=False)

# Display the first few rows of the DataFrame with the columns 'age' and 'age_group'
print(stroke_data2[['age', 'age_group']].head())

    age age_group
0  67.0     61-80
1  61.0     61-80
2  80.0       81+
3  49.0     41-60
4  79.0     61-80

# PREVALENCE OF HEART DISEASE ACROSS AGE GROUP

# Set the figure size
plt.figure(figsize=(12, 6))

# Define the custom color palette
custom_palette = ['#FF4500', '#252E6C']  # Colors swapped compared to the previous code

# Plot a countplot with Seaborn
sns.countplot(x="age_group", hue="heart_disease", data=stroke_data2, palette=custom_palette)

# Add a title to the plot
plt.title("Prevalence of Heart Disease Across Age Groups")  # Title modified

# Add labels for the x-axis and y-axis
plt.xlabel("Age Group")
plt.ylabel("Count")

# Enable grid on the plot
plt.grid(True)

# Change the order of labels in the legend
plt.legend(title="Heart Disease", labels=["Yes", "No"])

# Rotate the labels on the x-axis for better readability
plt.xticks(rotation=45)

# Show the plot
plt.show()

# AGE BY HYPERTENSION

# Replace the values in the 'hypertension' column with strings
stroke_data['hypertension'] = stroke_data['hypertension'].replace({1: 'Yes', 0: 'No'})

# Create a histogram with Plotly Express
fig = px.histogram(
    stroke_data,  # Use the data from stroke_data
    x='age',  # Data to be displayed on the x-axis
    color='hypertension',  # Color the bars based on the 'hypertension' column
    barmode='overlay',  # Overlay the bars
    title='Distribution of Age by Hypertension Status',  # Title of the plot (modified)
    labels={'hypertension': 'Hypertension', 'age': 'Age'},  # Rename the axis labels
    nbins=30,  # Number of bins for the histogram
    color_discrete_map={'Yes': '#252E6C', 'No': '#BC3030'}  # Custom colors for each category of 'hypertension'
)

# Show the plot
fig.show()

# HYPERTENSION BY SMOKING STATUS

# Filter the data to keep only cases where hypertension is "Yes"
yes_hypertension_stroke_data = stroke_data2[stroke_data2['hypertension'] == 'Yes']

# Count the occurrences of each value of smoking_status
hypertension_by_smoking = yes_hypertension_stroke_data['smoking_status'].value_counts().reset_index()

# Rename the columns of the resulting DataFrame
hypertension_by_smoking.columns = ['Smoking_Status', 'Count']

# Define a custom color palette for the plot
custom_colors = ['#FF6347', '#32CD32', '#FFD700', '#4682B4']

# Create a pie chart with Plotly Express
fig = px.pie(
    hypertension_by_smoking,  # Use the data from hypertension_by_smoking
    names='Smoking_Status',  # Names of the pie chart slices are determined by the values in the 'Smoking_Status' column
    values='Count',  # Values of the pie chart slices are determined by the values in the 'Count' column
    title="Hypertension Cases by Smoking Status",  # Title of the plot (modified)
    color_discrete_sequence=custom_colors,  # Use the custom color palette
    labels={'Smoking_Status': 'Smoking Status', 'Count': 'Count'}  # Rename the axis labels
)

# Show the plot
fig.show()

# Count the occurrences of each value in the 'smoking_status' column
stroke_data2['smoking_status'].value_counts()

smoking_status
never smoked       1892
Unknown            1544
formerly smoked     885
smokes              789
Name: count, dtype: int64

# BMI AND AVERAGE GLUCOSE BY STROKE

# Define a custom color map for the values in the 'stroke' column
color_discrete_map_inverted = {'Yes': '#FF4500', 'No': '#252E6C'}

# Create a scatter plot with Plotly Express
fig = px.scatter(
    stroke_data,  # Use the data from stroke_data
    x='bmi',  # The x-axis values are defined by the 'bmi' column
    y='avg_glucose_level',  # The y-axis values are defined by the 'avg_glucose_level' column
    color='stroke',  # Points are colored based on the values in the 'stroke' column
    title='BMI and Average Glucose Level vs. Stroke',  # Title of the plot
    labels={'bmi': 'BMI', 'avg_glucose_level': 'Average Glucose Level', 'stroke': 'Stroke'},  # Rename axis labels
    color_discrete_map=color_discrete_map_inverted,  # Use the custom color map
    width=1000,  # Set the width of the plot
    height=600  # Set the height of the plot
)

# Update the layout of the plot to specify the legend font size
fig.update_layout(
    legend=dict(
        font=dict(
            size=12,  # Legend font size
        )
    )
)

# Show the plot
fig.show()

	id	age	hypertension	heart_disease	avg_glucose_level	bmi	stroke
count	5110.000000	5110.000000	5110.000000	5110.000000	5110.000000	4909.000000	5110.000000
mean	36517.829354	43.226614	0.097456	0.054012	106.147677	28.893237	0.048728
std	21161.721625	22.612647	0.296607	0.226063	45.283560	7.854067	0.215320
min	67.000000	0.080000	0.000000	0.000000	55.120000	10.300000	0.000000
25%	17741.250000	25.000000	0.000000	0.000000	77.245000	23.500000	0.000000
50%	36932.000000	45.000000	0.000000	0.000000	91.885000	28.100000	0.000000
75%	54682.000000	61.000000	0.000000	0.000000	114.090000	33.100000	0.000000
max	72940.000000	82.000000	1.000000	1.000000	271.740000	97.600000	1.000000

Task 1

Task 2

Task 3

Task 4

	id	gender	age	hypertension	heart_disease	ever_married	work_type	Residence_type	avg_glucose_level	bmi	smoking_status	stroke
0	9046	Male	67.0	0	1	Yes	Private	Urban	228.69	36.6	formerly smoked	1
1	51676	Female	61.0	0	0	Yes	Self-employed	Rural	202.21	NaN	never smoked	1
2	31112	Male	80.0	0	1	Yes	Private	Rural	105.92	32.5	never smoked	1
3	60182	Female	49.0	0	0	Yes	Private	Urban	171.23	34.4	smokes	1
4	1665	Female	79.0	1	0	Yes	Self-employed	Rural	174.12	24.0	never smoked	1